Non-negative matrix completion for action detection

• Developing a multi-label classification framework with a convex optimization process for activity detection.
• Histogram correction for activity representation in each class, to localize activities in a weakly supervised setting.
• Proposing a new formulation for matrix completion to deal with classification/localization in video.
• Developing an activity recognition system in a totally weakly supervised multi-label setting.
• Developing a non-negative matrix completion framework based on Alternating Direction Method (ADM).

With the increasing number of videos all over the Internet and the increasing number of cameras looking at people around the world, one of the most interesting applications would be human activity recognition in videos. Many researches have been conducted in the literature for this purpose. But, still recognizing activities in a video with unrestricted conditions is a challenging problem. Moreover, finding the spatio-temporal location of the activity in the video is another issue. In this paper, we present a method based on a non-negative matrix completion framework, that learns to label videos with activity classes, and localizes the activity of interest spatio-temporally throughout the video. This approach has a multi-label weakly supervised setting for activity detection, with a convex optimization procedure. The experimental results show that the proposed approach is competitive with the state-of-the-art methods.